© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15321
    Prev
    Next
    INDEX
    Explanations

    say 8

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kang
    -18.25
    震荡
    -16.75
    Hang
    -16.63
    华盛
    -16.38
     crash
    -16.13
     Lancaster
    -16.13
     Pend
    -16.00
     Reagan
    -15.94
     Boom
    -15.63
    TER
    -15.38
    POSITIVE LOGITS
    isseur
    19.63
     chest
    18.50
     Dixon
    17.50
     Dalton
    16.50
     Ethi
    16.38
    绰
    16.38
     Schro
    16.25
     GX
    16.13
    chest
    16.13
    chal
    16.00
    Activations Density 0.044%

    No Known Activations